Hello, I am Jiahao Yuan, currently studying Artificial Intelligence at East China Normal University (ECNU). I received my bachelor’s degree in Computer Science and Technology from University of Shanghai for Science and Technology (USST).

My research interests broadly lie in enhancing reasoning capabilities of LLMs/MLLMs through post-training and agent rl, and aligning model capabilities across tasks and behaviors robustly in complex real-world environments. My long-term goal is to develop reasoning alignment and social alignment AI systems that benefit society.

I have published 7 papers in top international AI conferences such as ACL, AAAI, WWW, and MM, including associated competitions. I am also excited to announce the release of our newest empathetic LLM, Kardia-R1. As the lead contributor and first author during my internship at Ant Group, I represented the team in releasing 2 technical reports: Query as Anchor & How do decoder-only llm perceive user?. I am currently seeking job opportunities related to LLM.

Feel free to reach out via email at jamse_yuan@163.com πŸ€— for relevant opportunities or potential collaborations β€”β€” I’m always open to research discussions!

πŸ”₯ News

  • 2026.05: Β πŸŽ‰πŸŽ‰ Our Query-as-Anchor accepted to KDD 2026 !!!

  • 2026.03: Β πŸŽ‰πŸŽ‰ Our ATLAS (agent rl for routing) accepted to ACL 2026 Finding !!! Congratulations to Wu !

  • 2026.02: Β πŸŽ‰πŸŽ‰ Completed my 6‑month internship at Ant Group (ended Jan 2026) and published two technical reports (Query as Anchor & How do decoder-only llm perceive user?). Special thanks to the DeepFind team!

  • 2026.01: Β πŸŽ‰πŸŽ‰ Our Kardia-R1 accepted to WWW 2026 !!!

  • 2025.11: Β πŸŽ‰πŸŽ‰ One paper accepted to AAAI 2026 !!!

  • 2025.07: Β πŸŽ‰πŸŽ‰ One paper accepted to ACM Multimedia 2025 !!!

  • 2025.05: Β πŸŽ‰πŸŽ‰ Two papers accepted to ACL 2025 Main Conference !!!

  • 2025.05: Β πŸŽ‰πŸŽ‰ Achieved 3rd place πŸ† in the XLLM@ACL2025 Shared Task-III: LLM for Structural Reasoning!

  • Ongoing πŸ› οΈ Maintainer, Awesome-LLM-Empathy β€” a curated list of LLM resources for empathy and affective computing GitHub Repo stars

πŸ“ Publications (* Indicates Equal Contribution, † Indicates Project Leader)

Tech Report
ggsm

How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning

Jiahao Yuan †, Yike Xu, Jinyong Wen, Baokun Wang, Yang Chen, Xiaotong Lin, Wuliang Huang, Ziyi Gao, Xing Fu, Yu Cheng, Weiqiang Wang

Tech Report (Ant Group) | Code

KDD 2026
q-anchor

Query-as-Anchor: Scenario-Adaptive User Representation via Large Language Model

Jiahao Yuan †, Yike Xu, Jinyong Wen, Baokun Wang, Ziyi Gao, Xiaotong Lin, Yun Liu, Xing Fu, Yu Cheng, Yongchao Liu, Weiqiang Wang, Zhongle Xie

Tech Report (Ant Group) & KDD 2026 | Code

WWW 2026
kardia

Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning

Jiahao Yuan †, Zhiqing Cui, Hanqing Wang, Yuansheng Gao, Yucheng Zhou, Usman Naseem

WWW 2026 | Code

Arxiv
culturalpalette

Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette

Jiahao Yuan, Zixiang Di, Shangzixin Zhao, Zhiqing Cui, Hanqing Wang, Guisong Yang, Usman Naseem

Under Review

Arxiv
Prune_on_Logic

Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning

Shangziqi Zhao*, Jiahao Yuan* †, Jinyang Wu*, Zhenglin Wang, Guisong Yang, Usman Naseem

Under Review | Code

MM 2025
draw

Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation

Zhiqing Cui*, Jiahao Yuan*, Hanqing Wang, Yanshu Li, Chenxu Du, Zhenglong Ding

ACM MM 2025 Oral

ACL 2025
rot

Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up

Jiahao Yuan, Dehui Du, Hao Zhang, Zixiang Di, Usman Naseem

ACL 2025 Main | Code

ACL 2025
reflectdiffu
LLMSR@XLLM25
sym

LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation

Jiahao Yuan, Xingzhe Sun, Xing Yu, Jingwen Wang, Dehui Du, Zhiqing Cui, Zixiang Di

XLLM@ACL (Challenge, 3rd Place) 2025 | Code

AAAI 2026
affr1

Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model

Hanqing Wang, Shaoyang Wang, Yiming Zhong, Zemin Yang, Jiamin Wang, Zhiqing Cui, Jiahao Yuan, Yifan Han, Mingyu Liu, Yuexin Ma AAAI 2026 Oral

Other Paper

πŸŽ– Honors and Awards

  • 2023–2024 First-Class Scholarship for Academic Excellence in USST
  • 2023 IoT Track, Chinese Collegiate Computing Competition, First Prize
  • 2023 Software Application Development Track, Chinese Collegiate Computing Competition, Third Prize
  • 2023 China Collegiate Computing Contest-Network Technology Challenge, Third Prize
  • 2022–2023 First-Class Scholarship for Academic Excellence in USST
  • 2021–2022 Outstanding Student in USST
  • 2020–2021 First-Class Scholarship for Academic Excellence in USST

πŸ“– Educations

  • 2024.06 - now, Artificial Intelligence, East China Normal University.
  • 2020.09 - 2024.06, Computer Science & Technology, University of Shanghai for Science and Technology.

✍️ Service

  • Reviewer: ACL (2025-2026); EMNLP (2025-2026); AAAI (2026); WWW (2025-2026); KDD (2026); IJCAI (2025)

πŸ’» Internships

  • 2024.07-2024.11, ByteDance, Living Services Department – User Growth Algorithm Intern
  • 2025.06-2026.01, Ant Group, User Understanding and Representation Large Model Research Intern
  • 2026.01-2026.04, ByteDance, Douyin Group ,Content Understanding LLM Byteintern